English

Self-Supervised Speaker Verification Using Dynamic Loss-Gate and Label Correction

Sound 2022-08-04 v1 Audio and Speech Processing

Abstract

For self-supervised speaker verification, the quality of pseudo labels decides the upper bound of the system due to the massive unreliable labels. In this work, we propose dynamic loss-gate and label correction (DLG-LC) to alleviate the performance degradation caused by unreliable estimated labels. In DLG, we adopt Gaussian Mixture Model (GMM) to dynamically model the loss distribution and use the estimated GMM to distinguish the reliable and unreliable labels automatically. Besides, to better utilize the unreliable data instead of dropping them directly, we correct the unreliable label with model predictions. Moreover, we apply the negative-pairs-free DINO framework in our experiments for further improvement. Compared to the best-known speaker verification system with self-supervised learning, our proposed DLG-LC converges faster and achieves 11.45%, 18.35% and 15.16% relative improvement on Vox-O, Vox-E and Vox-H trials of Voxceleb1 evaluation dataset.

Keywords

Cite

@article{arxiv.2208.01928,
  title  = {Self-Supervised Speaker Verification Using Dynamic Loss-Gate and Label Correction},
  author = {Bing Han and Zhengyang Chen and Yanmin Qian},
  journal= {arXiv preprint arXiv:2208.01928},
  year   = {2022}
}

Comments

Accepted by Interspeech 2022

R2 v1 2026-06-25T01:26:26.239Z